Objective:To develop and evaluate a deep learning-based automatic measurement model for panoramic ultrasound biomicroscopy (UBM) images.Methods:A diagnostic test study was conducted.Preoperative UBM examination results of 372 patients who underwent implantable collamer lens (ICL) implantation were collected at the Eye Center of Renmin Hospital of Wuhan University between February 2021 and March 2023.A total of 1 368 panoramic UBM images were obtained to establish an image database.The dataset was divided into a training set (760 images), a validation set (86 images) and an internal test set (522 images).An expert panel consisting of three ophthalmologists annotated the images.The UNet+ + network was used to automatically segment anterior segment tissues, such as the cornea, lens and iris.In addition, image processing techniques and geometric localization algorithms were developed to automatically identify the anatomical landmarks of pupil diameter (PD), anterior chamber depth (ACD), angle-to-angle distance (ATA) and sulcus-to-sulcus distance (STS) to complete the measurement of these parameters.Additionally, 480 panoramic UBM images of 135 patients (240 eyes) from Aier Eye Hospital of Wuhan University were used as an external test set to further evaluate the performance of the model in different centers.The consistency between the measurements from the model and expert panel, the Pentacam system was assessed.Finally, 150 images were randomly selected from the external test set for a human-machine comparison to further evaluate the model's performance.This study adhered to the Declaration of Helsinki.The study protocol was approved by the Ethics Committee of Renmin Hospital of Wuhan University (No.WDRY-2022-K109) and Aier eye Hospital of Wuhan University (No.2023IRBKY120903).Written informed consent was obtained from each subject.Results:In the internal test dataset and external test dataset, with manual labeling as the reference standard, the model achieved a mean Dice coefficient of not less than 0.882.At least 95.65% of the anatomical landmark localization results had Euclidean distance differences within 250 μm.The intraclass correlation coefficients (ICCs) for the measurements of PD, ACD, angle-to-angle ATA, and STS were at least 0.958, with mean relative errors not exceeding 2.407%.With the Pentacam measurements as the reference standard, the ICCs for PD in the internal and external test sets were 0.540 and 0.466, respectively, while the ICCs for ACD were 0.946 and 0.908, respectively.In the human-machine comparison, the ICCs between the model's measurements and those of senior experts were all not lower than 0.969.Conclusions:The deep learning-based model can automatically measure anterior segment parameters from preoperative panoramic UBM images of patients undergoing ICL surgery.The model demonstrates a consistency comparable to that of senior experts, while providing higher efficiency.In terms of ACD measurement, the model shows good agreement between the measurements obtained from the model and Pentacam system.

Objective:To develop and evaluate a deep learning-based automatic measurement model for panoramic ultrasound biomicroscopy (UBM) images.Methods:A diagnostic test study was conducted.Preoperative UBM examination results of 372 patients who underwent implantable collamer lens (ICL) implantation were collected at the Eye Center of Renmin Hospital of Wuhan University between February 2021 and March 2023.A total of 1 368 panoramic UBM images were obtained to establish an image database.The dataset was divided into a training set (760 images), a validation set (86 images) and an internal test set (522 images).An expert panel consisting of three ophthalmologists annotated the images.The UNet+ + network was used to automatically segment anterior segment tissues, such as the cornea, lens and iris.In addition, image processing techniques and geometric localization algorithms were developed to automatically identify the anatomical landmarks of pupil diameter (PD), anterior chamber depth (ACD), angle-to-angle distance (ATA) and sulcus-to-sulcus distance (STS) to complete the measurement of these parameters.Additionally, 480 panoramic UBM images of 135 patients (240 eyes) from Aier Eye Hospital of Wuhan University were used as an external test set to further evaluate the performance of the model in different centers.The consistency between the measurements from the model and expert panel, the Pentacam system was assessed.Finally, 150 images were randomly selected from the external test set for a human-machine comparison to further evaluate the model's performance.This study adhered to the Declaration of Helsinki.The study protocol was approved by the Ethics Committee of Renmin Hospital of Wuhan University (No.WDRY-2022-K109) and Aier eye Hospital of Wuhan University (No.2023IRBKY120903).Written informed consent was obtained from each subject.Results:In the internal test dataset and external test dataset, with manual labeling as the reference standard, the model achieved a mean Dice coefficient of not less than 0.882.At least 95.65% of the anatomical landmark localization results had Euclidean distance differences within 250 μm.The intraclass correlation coefficients (ICCs) for the measurements of PD, ACD, angle-to-angle ATA, and STS were at least 0.958, with mean relative errors not exceeding 2.407%.With the Pentacam measurements as the reference standard, the ICCs for PD in the internal and external test sets were 0.540 and 0.466, respectively, while the ICCs for ACD were 0.946 and 0.908, respectively.In the human-machine comparison, the ICCs between the model's measurements and those of senior experts were all not lower than 0.969.Conclusions:The deep learning-based model can automatically measure anterior segment parameters from preoperative panoramic UBM images of patients undergoing ICL surgery.The model demonstrates a consistency comparable to that of senior experts, while providing higher efficiency.In terms of ACD measurement, the model shows good agreement between the measurements obtained from the model and Pentacam system.

Objective:To This study was to investigate the expression and possible clinical significance of microRNA-146b (miR-146b) and signal transducer and transcriptional activator 1 and 3 (STAT1/3) in peripheral blood mononuclear cells (PBMCs) of patients with primary gouty arthritis (GA).Methods:The peripheral blood samples, clinical data and laboratory indexes of 120 male cases of GA [including 57 cases of acute (AG group) and 63 cases of intermittent (IG group)]and 66 healthy subjects (HC group) were collected. The expression levels of miR-146b and STAT1/3 in PBMCs were detected by real-time fluorescence quantitative PCR (RT-qPCR). The differences among the three groups were compared and the correlation between them and clinical indexes was analyzed. The receiver operating characteristic curve (ROC) was constructed to evaluate its diagnostic value in GA. After the PBMCs of 18 healthy subjects were stimulated by 100 μg/ml MSU for 3 hours to simulate acute gout inflammatory environment, the transcriptional changes of IL-1β, miR-146b and STAT1/3 were detected by RT-qPCR, and the expressions of IL-1β, STAT1/3 protein and phosphorylated protein were detected by Western blotting. T test or one-way ANOVA and LSD- t test were used in accordance with the normal measurement data, Kruskal-Wallis H and Mann-Whitney U test were used in the non-normal data, Spearman correlation analysis was used in the correlation between variables, and the diagnostic value was evaluated by the receiver working characteristic curve ROC. Results:①There were statistical differences in the expression of miR-146b, STAT1 and STAT3 among the three groups ( F=7.02、19.52、17.07, all P<0.001). The expression of miR-146b in gout group [(0.32±0.28)] was significantly higher than that in HC group (0.19±0.18)( t=2.96, P=0.003), while STAT1(0.019±0.012) and STAT3(0.014±0.010) were significantly lower than those in HC group (0.038±0.029),(0.025±0.016)( t=6.26, 5.56, both P<0.001). Further subgroup analysis showed that the expression of miR-146b in AG and IG groups was higher than that in HC group[(0.27±0.17), (0.38±0.35), (0.19±0.18), t=2.09, 3.30, both P<0.05], but that in AG group was lower than that in IG group ( t=2.02, P<0.05). The expression of STAT1 mRNA in AG and IG groups was lower than that in HC group [(0.020±0.012), (0.019±0.012), (0.038±0.029), t=4.89, 4.56, both P<0.001], but there was no statistical significance between AG and IG groups ( t=0.24, P>0.05). The expression of STAT3 mRNA in AG and IG groups was lower than that in HC group [(0.016±0.012), (0.012±0.008), (0.025±0.016), t=5.64, 3.33, both P<0.01], and the expression of STAT3 mRNA in AG group was higher than that in IG group ( t=2.12, P<0.05). ② Spearman correlation analysis showed that the expression of miR-146b in GA was negatively correlated with HCY ( r=-0.37, P=0.014), STAT1 was negatively correlated with Crea ( r=-0.29, P=0.019), positively correlated with eGFR ( r=0.25, P=0.047), and STAT3 was negatively correlated with HDL-C ( r=-0.27, P=0.033). ③ROC curve showed that the AUC (95% CI) of miR-146b, STAT1 and STAT3 were 0.679(0.582, 0.776), 0.710(0.629, 0.791) and 0.705(0.626, 0.783), and the combined AUC(95% CI) of the three was 0.836 (0.765, 0.907). ④Compared with blank control group and negative control group, the expression of miR-146b in PBMCs of 18 cases of HC was significantly decreased ( H=14.44, P=0.003), while the expression of IL-1β, STAT1 and STAT3 mRNA was significantly increased after 3 h of MSU stimulation ( H=26.44、27.26、15.90, all P<0.001). The expression of IL-1β, STAT1 and STAT3 protein and phosphorylated protein in the model group were significantly higher than those in the blank control group, and the differences were statistically significant ( t=9.97、6.63、7.48、11.25、6.28, all P<0.01). Conclusion:The abnormal expression of miR-146b and STAT1/3 in GA is related to some clinical indicators, suggesting that it may be involved in the regulation of gout immune inflammatory response and metabolism, and the specific mechanism is worth further study.

DNA methylation is an epigenetic modification that forms an important regulation mechanism of gene expression in organisms across kingdoms. Aberrant patterns of DNA methylation can lead to plant developmental abnormalities. In this article, we briefly discuss DNA methylation in plants and summarize its functions and biological roles in regulating gene expression and maintaining genomic stability, plant development, as well as plant responses to biotic and abiotic stresses. We intended to provide a concise reference for further understanding of the mechanism of DNA methylation and potential applications of epigenetic manipulation for crop improvement.
Crop Production ; trends ; DNA Methylation ; Epigenesis, Genetic ; Gene Expression Regulation, Plant ; Genomic Instability ; Plants ; genetics ; Research ; trends ; Stress, Physiological